One person is driving this. The headline number reflects a single contributor's workflow, not a project-wide shift.
Assisted or autonomous
Assisted — a developer’s identity authored the commit and the agent added itself as co-author. The agent ran git commit during a working session, with a person there. Autonomous — a bot identity is the author, no human in the loop. Across the whole index, 93.7% of agent commits are assisted.
Agent share by month
Peak month: 5.1%. Bars are scaled to that peak, not to 100%.
Which agents
| Cursor Agent | Anysphere | 3 | 0.6% |
| Claude Code | Anthropic | 2 | 0.4% |
Verify it yourself
Sample commits that matched. Every one links to GitHub — check the trailers.
a5190db6chore: remove unused repo assets (#5389)Cursor Agent6d6609b8feat: add solutions to lc problem: No.3225 (#5388)Cursor Agentf7a3261afeat: add solutions to lc problems: No.4034~4035Cursor Agent4f7bd518feat: add CLAUDE.md and AGENTS.md for AI coding assistants (#5220)Claude Code66bcf158feat: add rust solution to lc No.3093 (#5218)Claude Code
What was excluded
| Commits in window | 564 |
| Merge commits removed | −0 |
| CI / dependency bots removed | −26 |
| Considered | 538 |
Bots are excluded from the denominator entirely. Counting dependabot as “AI-written code” is the fastest way to produce a meaningless number.
How this was measured
Measured over February–August 2026, cloned directly. Detection is deterministic string matching against signatures agents write about themselves — no heuristics, no style analysis. Merge commits and CI bots are excluded from the denominator. The figure is a floor: squash merges strip trailers, so real usage is higher. Contributor counts are aggregate — no individual is named.
Run it yourself: npx qmmit-cli doocs/leetcode